def gpa_letter_converter(gpa):
letter_grades = {
"A": 4.0,
"A-": (3.7, 3.8, 3.9),
"B+": (3.3, 3.4, 3.5, 3.6),
"B": (3.0, 3.1, 3.2),
"B-": (2.7, 2.8, 2.9),
"C+": (2.3, 2.4, 2.5, 2.6),
"C": (2.0, 2.1, 2.2),
"C-": (1.7, 1.8, 1.9),
"D": (1.0, 1.1, 1.2, 1.3, 1.4, 1.5, 1.6),
"F": (0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9)
}
for letter_grade, number_grade in letter_grades.items():
if isinstance(number_grade, float) and gpa == number_grade:
return letter_grade
elif isinstance(number_grade, tuple) and gpa in number_grade:
return letter_grade
return None
def calculate_average_gpas(df):
# Prepare a list to store the results
results = []
# GPA equivalents for each letter grade
letter_grades_to_gpa = {
"A+": 4.0,
"A": 4.0,
"A-": 3.7,
"B+": 3.3,
"B": 3.0,
"B-": 2.7,
"C+": 2.3,
"C": 2.0,
"C-": 1.7,
"D": 1.0,
"F": 0.0
}
# Loop over all unique course numbers
for class_nbr in df["NBR"].unique():
# Filter the DataFrame for the current course number
df_nbr = df[df["NBR"] == class_nbr]
# Loop over all unique professors for the current course number
for prof in df_nbr["PROF"].unique():
# Filter the DataFrame for the current professor
df_prof = df_nbr[df_nbr["PROF"] == prof]
# Calculate the average GPA for the current professor and course number
avg_gpa_prof = round(df_prof["AVG GPA"].mean(), 1)
# Convert the individual grade counts to GPA equivalents and calculate the standard deviation
gpa_distributions = []
for grade_letter, gpa in letter_grades_to_gpa.items():
gpa_distributions.extend([gpa] * df_prof[grade_letter].sum())
std_dev_gpa_prof = round(np.std(gpa_distributions), 2)
# Append the result to the list
results.append({
"CLASS NUMBER": class_nbr,
"PROF": prof,
"AVG GPA PROF": avg_gpa_prof,
"AVG GPA PROF LETTER": gpa_letter_converter(avg_gpa_prof),
"STD DEV GPA PROF": std_dev_gpa_prof
})
# If there is more than one professor for this course, calculate the average GPA for the current course number, regardless of the professor
if df_nbr["PROF"].nunique() > 1:
avg_gpa_nbr = round(df_nbr["AVG GPA"].mean(), 1)
# Convert the individual grade counts to GPA equivalents and calculate the standard deviation
gpa_distributions = []
for grade_letter, gpa in letter_grades_to_gpa.items():
gpa_distributions.extend([gpa] * df_nbr[grade_letter].sum())
std_dev_gpa_nbr = round(np.std(gpa_distributions), 2)
# Append the result to the list
results.append({
"CLASS NUMBER": class_nbr,
"PROF": "All Professors",
"AVG GPA PROF": avg_gpa_nbr,
"AVG GPA PROF LETTER": gpa_letter_converter(avg_gpa_nbr),
"STD DEV GPA PROF": std_dev_gpa_nbr
})
# Convert the list of results to a DataFrame
df_results = pd.DataFrame(results)
# Find the hardest class based on average GPA
hardest_class = df_results[df_results["PROF"] == "All Professors"].sort_values("AVG GPA PROF").iloc[0]
# Calculate the average GPA for the entire subject
avg_gpa_subject = round(df["AVG GPA"].mean(), 1)
print(f"The average GPA for this entire subject in Spring 2023 was: {avg_gpa_subject}, which is equal to a {gpa_letter_converter(avg_gpa_subject)}")
print(f"The hardest class based on average GPA in Spring 2023 was ACCT {hardest_class['CLASS NUMBER']} with an average GPA of {hardest_class['AVG GPA PROF']}, which is equal to a {hardest_class['AVG GPA PROF LETTER']}")
print("\nStandard deviation tells us about the spread of the grades that students received in each class. A higher standard deviation indicates a wider range of grades, while a lower standard deviation indicates that grades were more closely clustered around the average.")
return df_results
def calculate_teacher_gpas(df):
# Prepare a list to store the results
results = []
# GPA equivalents for each letter grade
letter_grades_to_gpa = {
"A+": 4.0,
"A": 4.0,
"A-": 3.7,
"B+": 3.3,
"B": 3.0,
"B-": 2.7,
"C+": 2.3,
"C": 2.0,
"C-": 1.7,
"D": 1.0,
"F": 0.0
}
# Loop over all unique professors
for prof in sorted(df["PROF"].unique()):
# Filter the DataFrame for the current professor
df_prof = df[df["PROF"] == prof]
# Calculate the average GPA for the current professor
avg_gpa_prof = round(df_prof["AVG GPA"].mean(), 1)
# Convert the individual grade counts to GPA equivalents and calculate the standard deviation
gpa_distributions = []
for grade_letter, gpa in letter_grades_to_gpa.items():
gpa_distributions.extend([gpa] * df_prof[grade_letter].sum())
std_dev_gpa_prof = round(np.std(gpa_distributions), 1)
# Calculate the percentage of students who withdrew for the current professor
withdraw_percentage = df_prof["W"].sum() / df_prof["TOTAL"].sum()
# Append the result to the list
results.append({
"PROF": prof,
"AVG GPA PROF": avg_gpa_prof,
"AVG GPA PROF LETTER": gpa_letter_converter(avg_gpa_prof),
"STD DEV GPA PROF": std_dev_gpa_prof,
"NUM OF CLASSES": len(df_prof),
"WITHDRAW PERCENTAGE": round(withdraw_percentage * 100, 1)
})
# Convert the list of results to a DataFrame
df_results = pd.DataFrame(results)
# Calculate the average GPA for the entire subject
avg_gpa_subject = round(df["AVG GPA"].mean(), 1)
# Calculate the average standard deviation for the entire subject
gpa_distributions = []
for grade_letter, gpa in letter_grades_to_gpa.items():
gpa_distributions.extend([gpa] * df[grade_letter].sum())
avg_std_dev_subject = round(np.std(gpa_distributions), 1)
# Calculate the average withdrawal percentage for the entire subject
withdraw_percentage_subject = round((df["W"].sum() / df["TOTAL"].sum()) * 100, 2)
# Find the professors who teach more than one class, have a GPA that is the same or higher than the subject average GPA,
# and for whom less than 40% of students withdrew
best_profs = df_results[(df_results["NUM OF CLASSES"] > 1) & (df_results["AVG GPA PROF"] >= avg_gpa_subject) & (df_results["WITHDRAW PERCENTAGE"] <= withdraw_percentage_subject)]
print(f"Professors who teach more than one class, have a GPA that is the same or higher than the subject average GPA ({avg_gpa_subject}), and have a withdrawal percentage that is less or equal than the subject average withdrawal percentage ({withdraw_percentage_subject}%):\n")
print(best_profs, "\n")
print("Please note that this automated analysis does not take ratings from RMP (RateMyProfessors) into account. While the provided statistics are based on GPA, it cannot conclude the amount of material students learned from each professor.\n")
print(f"The average standard deviation of GPA for all professors in this subject in Spring 2023 was: {avg_std_dev_subject}")
return df_results
